Course syllabus

Course-PM

EEN096 Artificial intelligence and autonomous systems lp1 HT23 (7.5 hp)

The course is offered by the Department of Electrical Engineering

Contact details

Examiner:

Dr. Emmanuel Dean (deane@chalmers.se)

Lecturers:

• Dr. Emmanuel Dean (deane@chalmers.se)
• Dr. Karinne Ramirez (karinne@chalmers.se)

TAs:

• M.Sc. Nanami Hashimoto (nanami@chalmers.se) 

Student Representatives: 

TIELL   Nawar.altouba@gmail.com   Nawar Altouba
TIMEL   bomanm@chalmers.se    Mikael Boman
TIELL   maketofake@gmail.com      Duc Thinh Dinh
TIMEL   mathiasgo@telia.com       Mathias Golebiak
UTBYTE  cesarmejiarota@gmail.com  Cesar Elias Mejia Rota

Course purpose

The course aims to provide a basic introduction to Artificial Intelligence (AI) and Machine Learning (ML) methods. Particular emphasis is on applications within robotics.

Course outline

This course consists of a total of 7 topics:

1. Search
2. Genetic Algorithms (GA)
3. Least Square Method Linear (LSML)
4. Least Square Methods Non-Linear (LSMNL)
5. Artificial Neural Networks (ANN)
6. Reinforcement Learning (RL)

Schedule

Nomenclature:

LX: Lecture X, e.g. L1 (Lecture 1)

EX: Exercise X, e.g., E2 (Exercise 2)

TX: Tutorial X, e.g., T3 (Tutorial 3)

AX: Assignment and Lab. Session X (Computer Exercises), e.g., A3 (Assignment and Computer Exercise 3)

DAX: Due date for Assignment X, e.g., DA3 (Due date for Assignment 3)

QX: Quizzes, e.g., Q2 (Quizz 2)

MP: Minute-paper activity

MM: Mentimeter activity

Full-Schedule:

TimeEdit

Course literature

The following list provides suggested literature for this course. This literature is not mandatory. It is intended to provide additional support for the course. Participants may use it to acquire more detailed information about the topics covered in this course.

[1] Artificial Intelligence: A Modern Approach, S. Jonathan Russell, P. Norvig, Pearson.
[2] Machine Learning. T. M. Mitchell, McGraw-Hill.

Course design

This lecture provides theoretical and practical information to understand and implement basic AI and Machine Learning methods.  The course comprises lectures (2x2 hours per week )[LX], exercises (2 hours per week)[EX], and home assignments with computer exercises (2 hours per week)[AX], including three tutorials (3x2 hours) [T1, T2, and T3].

Each assignment session will cover implementations in the form of practical and programming exercises in Matlab (m-files) and Simulink models. Therefore, the participants will require access to this software. Support for each assignment will be offered in the [AX] sessions. Each assignment has a due date defined in the schedule as [DAX]. At the end of Assignment 3, we will have a general Q&A session where the participants will be able to revise their acquired knowledge to prepare for the final group project. 

The main communication will be through the AX sessions (see schedule above) and Canvas.

Changes made since the last occasion

• The evaluation method has been updated to align with the course's ILOS. This course uses a group project as an evaluation method, instead of the written exam.

Learning objectives and syllabus

After completion of the course and given a set of basic AI/ML approaches, the students will be able to:

• define their principal advantages and disadvantages to differentiate them,
• classify them according to their application areas to identify how and when to use them, and
• interpret and implement them using a standard programming language.

Link to the syllabus on Studieportalen.

Study plan

Examination form

A group project composed of up to 3 students and approved home assignments are required to pass the entire course.

The examination will be divided into several parts, both for the Laboratory module and the lecture:

1. Compulsory Quizzes:
   During the course, you will need to complete a series of short quizzes. The quizzes aim to prepare the background knowledge required for the exercises or tutorials. The quizzes contain a few multiple-choice questions. To complete the quizzes, you must correctly answer more than 50% of the questions. You will have up to 3 attempts to get this score. 
   NOTE: You must complete all the quizzes to pass the Lab. The quizzes have strict due dates. Therefore, late submissions will not be accepted.
2. Compulsory laboratory Assignments (3 Assignments): The goal of these assignments is to provide practical experience in the implementation of basic AI and ML algorithms. The assignments will be delivered in teams (max. 2 participants). Each team has to deliver original material for the assignments in the form of m-files and/or Simulink models, depending on the assignment. The code must be accompanied by a short report that describes the delivered solution and how to run it (in the case the delivered material requires custom initialization).  In total, there will be 3 mandatory assignments and 1 optional assignment with bonus points for the group project. Each assignment will have tasks that can accumulate up to 10 assignment points (AP). There is a strict deadline for delivering each assignment marked as DAX in the schedule (see the above schedule). To pass the laboratory, you need to accumulate at least 21 AP and complete all the quizzes. 
   NOTE: Assignment 4 is not mandatory. However, the collected points in assignment 4 will be counted as bonus points in the group project, e.g., if you collect 10 AP, you will get 10/100 additional points in the project.
3. Compulsory Group Project: The goal of the group project is to allow the participants to demonstrate the acquired skills to understand and develop basic AI and ML solutions for a practical problem. The final group project will be based on the theory covered in the lectures [LX], the exercises  [EX], and the information within the tasks from the assignments [AX]. In the project, you will be able to get a total of 100 points. The grades for passing the project are:

   Number of Points	Project Grade
   84-100	5
   67-83	4
   50-66	3
   less than 50	fail

   The group project has two stages.
   
   1. Project Proposal Presentation (30%) [Mandatory]: 

      Each group must present the proposed project. Select a single complex problem that requires at least three of the five AI or ML methods taught in the course. The selected methods must address different parts of the same complex problem, not three unrelated problems. NOTE: The project presentation is mandatory. The presentation must include:

      1. Introduction and justification. What problem will you solve, and why is it important?

      2. Block diagram. Depict all AI or ML modules you plan to implement and show how they are interconnected.

      3. Module descriptions. For each module in the block diagram, specify:
         i) the AI or ML method to be implemented,
         ii) the input and output information for the module,
         iii) how the module connects to the other modules, and
         iv) which part of the overall problem does the module address?

      4. Deliverables. Define measurable outcomes for the project. You must specify at least three measurable outcomes that align with the selected AI or ML methods. You may include more if needed. These deliverables will be used to assess the project and to calculate the final grade.

   2. Project Presentation and Report (70%): 

      Each group presents the developed project and submits a written report. Include the following:

      1. Introduction.

      2. Initial project description. Summarize the original proposal and include the initial block diagram.

      3. Final block diagram. Present the modules actually implemented. If the final design differs from the original proposal, describe and justify the deviations.

      4. Results. Report the obtained results with appropriate evidence, for example, a demo video, plots, tables, or other evaluations of each target deliverable. Provide the implemented code with clear documentation to support grading.

      5. Individual contributions. Each member must clearly document their contributions.

      6. Conclusions and discussion.

4. Bonus Points for the group project: There are two ways to earn bonus points for the final project:
   a) Assignment 4. All points earned on Assignment 4 count as bonus points for the project.
   b) Minute Papers (MP). We will conduct four short reflections on course topics. Completing the four MPs provides up to four bonus points. 

IMPORTANT NOTES:

• Individual grading. Although the project is completed in groups, the final grade is individual. Documented individual contributions are a critical factor in the final grade.

• Use of large language models. If you use tools such as ChatGPT, you must include the following in your submission:

  1. Prompt. Provide the exact messages you used to obtain assistance.

  2. Original code generated by the tool. Append the unmodified code at the end of your project code as commented text. For inline copilots, include each inserted code snippet.

  3. Changes made and rationale. Describe how you modified the generated code and, more importantly, explain why you made those changes. Substantial modifications and documentation (made by you) are required for the code to be counted toward the final grade.

Further details and information will be given in the first lecture of this course.